New energy regional power prediction system based on extreme weather

Abstract

The invention discloses a new energy regional power prediction system based on extreme weather, relates to the technical field of new energy power prediction, and solves the technical problem of inaccurate power prediction caused by no consideration of errors in error relevance between historical power and meteorological data under extreme weather in the prior art. The method comprises the following steps: collecting historical weather data, corresponding historical regional power, historical power generation data and predicted weather data; comparing the historical weather data with a preset weather threshold range and analyzing historical extreme weather; constructing a power prediction model, identifying to obtain predicted extreme weather, and inputting the medical extreme weather and predicted weather data into the power prediction model to obtain predicted total power; and matching the predicted extreme weather with historical extreme weather to obtain a matched power generation means, obtaining matched power according to the matched power generation means, subtracting the matched power from the predicted total power to obtain non-clean energy power, and obtaining a non-clean energy consumption according to the non-clean energy power.

Description

Technical Field

[0001] The present invention belongs to the field of power prediction and relates to weather data analysis technology, and specifically to a new energy regional power prediction system based on extreme weather. Background Art

[0002] Environmental pollution and energy shortages have brought tremendous pressure to society, making environmental awareness gradually popular. More and more regions are encouraging the development of new energy industries, putting new energy development on the agenda, and new energy power generation will become an important development direction. Photovoltaic and wind power generation systems have become the main forms of modern new energy power generation, and the system energy power is greatly affected by weather data such as temperature, humidity, air pressure, solar radiation, wind speed and wind direction. In extreme weather, there is great uncertainty and randomness in weather changes, which will cause the new energy power generation system to be unable to operate stably.

[0003] The invention patent with application number CN2019108238078 discloses a regional short-term energy power prediction method and system taking weather into consideration. The invention obtains future meteorological data of a future date, and extracts historical meteorological data, historical network API meteorological data and measured historical power generation data that are the same as the future meteorological data from the database, and calculates historical total error data based on the historical meteorological data, historical network API meteorological data and measured historical power generation data; obtains real-time meteorological error, combines the historical total error data with the real-time meteorological data to obtain total meteorological error data, combines future meteorological data with the total meteorological error data to obtain predicted meteorological data, obtains power prediction data based on the predicted meteorological data, and optimizes the system power generation plan based on the power prediction data; when obtaining power prediction data, the invention only uses the total meteorological error data as a factor for power prediction, and does not take into account the historical power corresponding to the historical meteorology, especially in extreme weather, different extreme weathers correspond to different historical powers, and only considering the meteorological error data may lead to inaccurate predicted power.

[0004] The present invention provides a new energy regional power prediction system based on extreme weather to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a new energy regional power prediction system based on extreme weather, which is used to solve the technical problem in the prior art that inaccurate power prediction is caused by not taking into account the error correlation between historical power and meteorological data under extreme weather.

[0006] To achieve the above-mentioned object, a first aspect of the present invention provides a new energy regional power prediction system based on extreme weather, comprising: a database, a data collection module, a weather identification module and a power prediction module;

[0007] Data collection module: used to collect historical weather data, corresponding historical regional power, historical power generation data and forecast weather data;

[0008] Power prediction module: used to identify the corresponding historical extreme weather according to the historical weather data, and build a power prediction model based on the historical extreme weather, historical weather data and the corresponding historical regional power; identify the extreme weather corresponding to the predicted weather data, and input the extreme weather into the power prediction model to obtain the predicted total power;

[0009] Power generation analysis module: used to predict the use of non-clean energy based on the predicted total power, historical regional power, historical power generation data, historical weather data and predicted weather data.

[0010] Preferably, the identifying corresponding historical extreme weather according to historical weather data includes:

[0011] Extracting historical weather data; the historical weather data includes historical temperature, historical light, historical wind speed and historical rainfall;

[0012] Setting a weather threshold range; wherein the weather threshold is set according to weather data for distinguishing extreme weather; the weather threshold includes a light threshold range, a wind speed threshold range, a temperature threshold range and a rainfall threshold range;

[0013] Determine whether the historical temperature is within the temperature threshold range; if yes, mark the temperature state as a non-extreme temperature state; if no, mark the temperature state as an extreme temperature state;

[0014] Determine whether the historical wind speed is included in the wind speed threshold range; if yes, mark the wind speed state as a non-extreme wind speed state; if no, mark the wind speed state as an extreme wind speed state;

[0015] Determine whether the historical illumination is within the illumination threshold range; if yes, mark the illumination state as a non-extreme illumination state; if no, mark the illumination state as an extreme illumination state;

[0016] Determine whether the historical rainfall is within the rainfall threshold range; if yes, mark the rainfall state as a non-extreme rainfall state; if no, mark the rainfall state as an extreme rainfall state;

[0017] The temperature extreme state, wind speed extreme state, light extreme state and rainfall extreme state are marked as extreme states; the temperature state, wind speed state, light state and rainfall state are combined to obtain the weather state; the extreme states appearing in the weather state are analyzed to obtain the historical extreme weather.

[0018] Preferably, the step of analyzing the extreme conditions occurring in the weather conditions to obtain historical extreme weather conditions includes:

[0019] Extract extreme weather conditions and extract extreme weather comparison table from the database;

[0020] Match the extreme conditions with the extreme weather comparison table to obtain the historical extreme weather corresponding to the historical weather data.

[0021] Preferably, the power prediction model is constructed based on historical extreme weather, historical weather data and corresponding historical regional power, including:

[0022] Extract historical extreme weather, historical weather data and corresponding historical regional power;

[0023] Historical extreme weather, historical weather data and the corresponding historical regional power are used as training data and test data. The training data is used to train the neural network model, and the test data is used to test the trained neural network model. According to the test results, the parameters of the neural network model are adjusted to obtain a power prediction model whose input data is extreme weather and weather data, and whose output data is the corresponding regional power.

[0024] Preferably, the non-clean energy usage is predicted based on the predicted total power, historical regional power, historical power generation data, historical weather data and predicted weather data, including:

[0025] Extract forecast total power, historical regional power, historical power generation data, historical weather data, and forecast weather data;

[0026] Match the historical regional power and historical power generation data corresponding to historical extreme weather;

[0027] Identify the predicted weather state of the predicted weather data, and match the predicted weather state with the extreme weather comparison table to obtain the predicted extreme weather;

[0028] Determine whether the predicted extreme weather is the same as the historical extreme weather; if yes, mark the corresponding historical power generation data as matching power generation means; if no, mark the corresponding historical power generation data as not matching power generation means;

[0029] The matching power is obtained according to the matching power generation means; the non-clean energy power is obtained by subtracting the matching power from the corresponding predicted total power; and the non-clean energy consumption is obtained according to the non-clean energy power.

[0030] Preferably, obtaining matching power according to matching power generation means includes:

[0031] Extracting matching power generation means; the matching power generation means include solar power generation, hydropower generation, wind power generation and corresponding power generation under extreme weather conditions;

[0032] The average value of solar power generation is calculated to obtain solar power, the average value of hydroelectric power generation is calculated to obtain hydroelectric power, and the average value of wind power generation is calculated to obtain wind power;

[0033] Combine solar power, hydro power and wind power to get matching power.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention collects historical weather data, corresponding historical regional power, historical power generation data and predicted weather data; compares historical weather data with a preset weather threshold range to obtain weather conditions, analyzes extreme conditions in the weather conditions to obtain historical extreme weather, and can more accurately determine whether it is extreme weather, which can help formulate more effective adaptation strategies and help optimize energy production and distribution; constructs a power prediction model based on historical extreme weather, historical weather data and corresponding historical regional power, and identifies the extreme weather corresponding to the predicted weather data of the predicted date, inputs the extreme weather and predicted weather data into the power prediction model to obtain the predicted total power, which can more accurately predict the weather conditions under different weather conditions. The total power demand of the region under certain weather conditions; Identify the predicted weather status corresponding to the predicted weather data, and match it with the extreme weather comparison table to obtain the predicted extreme weather, mark the historical power generation data corresponding to the historical extreme weather that is the same as the predicted extreme weather as the matching power generation means, obtain the matching power according to the matching power generation means, subtract the matching power from the predicted total power to obtain the non-clean energy power, and obtain the non-clean energy usage according to the non-clean energy power. This can more accurately predict the total power demand of the region under specific weather conditions, especially extreme weather, make power dispatch more refined, reduce excess or shortage situations, and clarify the necessary usage of non-clean energy, which will help reduce greenhouse gas emissions and promote environmental protection.

[0036] 2. By identifying extreme weather on the predicted date and matching it with historical extreme weather corresponding to historical weather data, the present invention can help formulate more effective climate change adaptation strategies, help power companies optimize energy distribution, avoid power outages or waste caused by imbalance between supply and demand, and enhance the system's ability to resist extreme weather events. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1The following is a flowchart of an embodiment of the present invention.

[0039] Figure 2 It is a system composition diagram of the present invention.

[0040] Figure 3 The figure is a complete flow chart for obtaining weather conditions in one embodiment of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1-Figure 3 , the first aspect of the present invention provides a new energy regional power prediction system based on extreme weather, including: a database, a data collection module, a weather identification module and a power prediction module;

[0043] Data collection module: used to collect historical weather data, corresponding historical regional power, historical power generation data and predicted weather data.

[0044] Exemplarily, historical weather data in area A, the corresponding historical regional power, historical power generation data and weather forecast for area A are collected; the weather data of historical dates in the historical weather data are historical temperature of 25 degrees, historical light of 30,000 lux, historical wind speed of 0.1 meters per second, and historical rainfall of 400 mm per year.

[0045] In this embodiment, the illumination threshold range is set to 500 lux to 100,000 lux, the temperature threshold range is 0 degrees to 35 degrees, the wind speed threshold range is 0.2 meters per second to 30 meters per second, and the rainfall threshold range is 200 millimeters per year to 800 millimeters per year; it is determined whether the historical temperature is included in the temperature threshold range, and if it is determined that the historical temperature of the historical date is included in the temperature threshold range, then the temperature state of the historical date is a non-extreme temperature state; it is determined whether the historical wind speed is included in the wind speed threshold range, and if it is determined that the historical wind speed is not included in the wind speed threshold range, then the wind speed state of the historical date is an extreme wind speed state; it is determined whether the historical illumination is included in the illumination threshold range, and if it is determined that the historical illumination is included in the illumination threshold range, then the illumination state of the historical date is a non-extreme illumination state; it is determined whether the historical rainfall is included in the rainfall threshold range, and if it is determined that the historical rainfall is included in the rainfall threshold range, then the rainfall state of the historical date is a non-extreme rainfall state; the weather state of the historical date is obtained.

[0046] An extreme weather comparison table is extracted from the database. The extreme weather comparison table contains all extreme weathers that have occurred in history and the corresponding extreme conditions. By comparing the extreme conditions of the historical date with the corresponding extreme conditions in the extreme weather comparison table, it is found that the extreme weather corresponding to the historical date is windless weather.

[0047] It should be noted that extreme conditions can occur at the same time, such as extreme weather with no wind and drought or extreme weather with strong wind and cloudy weather; different power generation methods will be affected differently during different extreme weather conditions, such as lower electricity generation when there is no wind, lower hydropower generation during drought, and lower solar power generation on cloudy days.

[0048] Historical extreme weather, historical weather data and corresponding historical regional power are used as training data and test data, the training data is used to train the neural network model, and the test data is used to test the trained neural network model, and the parameters of the neural network model are adjusted according to the test results to obtain a power prediction model whose input data is extreme weather and weather data and whose output data is the corresponding regional power; the predicted weather data for the predicted date are a predicted temperature of 20 degrees, a predicted light of 100 lux, a predicted wind speed of 15 meters per second, and a predicted rainfall of 300 mm per year; the predicted weather data is compared with the weather threshold range to obtain the predicted weather state corresponding to the predicted weather data, which is an extreme light state, a non-extreme temperature state, a non-extreme wind speed state and a non-extreme rainfall state, and after matching with the extreme weather comparison table, the predicted extreme weather corresponding to the predicted weather data is cloudy, and the predicted extreme weather on the predicted date and the corresponding predicted weather data are input into the power prediction model as input data to obtain the predicted total power corresponding to the predicted date; in this embodiment, the predicted total power obtained is 110 megawatts.

[0049] The historical weather data and the corresponding historical regional power are classified and saved according to different extreme weather conditions, so that the corresponding weather data and regional power can be matched more quickly later.

[0050] Power generation analysis module: used to predict the use of non-clean energy based on the predicted total power, historical regional power, historical power generation data, historical weather data and predicted weather data.

[0051] Exemplarily, it is determined whether the predicted extreme weather is the same as the historical extreme weather, and the historical power generation data corresponding to the historical weather data that is cloudy and has the same weather data as the predicted weather data is marked as a matching power generation means. The wind power in the matching power generation means is 60 MW, the hydropower is 20 MW, and the solar power is 10 MW, so the matching power is 90 MW. The non-clean energy power is subtracted from the corresponding historical regional power to obtain 20 MW. The amount of coal required to produce 20 MW is 8.2 tons. The amount of other non-clean energy used varies depending on the type and other factors.

[0052] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0053] Working principle of the present invention:

[0054] The present invention collects historical weather data, corresponding historical regional power, historical power generation data and predicted weather data, compares the historical weather data with a preset weather threshold range to obtain weather status and extreme status, matches the extreme status in the weather status with an extreme weather comparison table to obtain the corresponding historical extreme weather; constructs a power prediction model based on the historical extreme weather, historical weather data and the corresponding historical regional power; compares the predicted weather data of the predicted date with the weather threshold range to obtain the predicted weather status, matches the predicted weather status with the extreme weather comparison table to obtain the predicted extreme weather, inputs the predicted weather status and the predicted weather data of the predicted extreme weather into the power prediction model to obtain the predicted total power; matches the predicted extreme weather with the historical extreme weather, marks the power generation means with the predicted extreme weather as the matching power generation means, obtains the corresponding matching power according to the matching power generation means, subtracts the matching power from the predicted total power to obtain the non-clean energy power, and calculates the non-clean energy usage according to the non-clean energy power.

[0055] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A new energy regional power prediction system based on extreme weather, characterized in that: include: Database, data collection module, weather identification module and power prediction module; Data collection module: used to collect historical weather data, corresponding historical regional power, historical power generation data and forecast weather data; Power prediction module: used to identify the corresponding historical extreme weather according to the historical weather data, and build a power prediction model based on the historical extreme weather, historical weather data and the corresponding historical regional power; identify the extreme weather corresponding to the predicted weather data, and input the extreme weather into the power prediction model to obtain the predicted total power; Power generation analysis module: used to predict the use of non-clean energy based on the predicted total power, historical regional power, historical power generation data, historical weather data and predicted weather data.

2. The extreme weather-based new energy regional power prediction system according to claim 1 is characterized in that: The identifying corresponding historical extreme weather according to historical weather data includes: Extracting historical weather data; the historical weather data includes historical temperature, historical light, historical wind speed and historical rainfall; Set the weather threshold range; the weather threshold includes the light threshold range, wind speed threshold range, temperature threshold range and rainfall threshold range; Determine whether the historical temperature is within the temperature threshold range; if yes, mark the temperature state as a non-extreme temperature state; if no, mark the temperature state as an extreme temperature state; Determine whether the historical wind speed is included in the wind speed threshold range; if yes, mark the wind speed state as a non-extreme wind speed state; if no, mark the wind speed state as an extreme wind speed state; Determine whether the historical illumination is within the illumination threshold range; if yes, mark the illumination state as a non-extreme illumination state; if no, mark the illumination state as an extreme illumination state; Determine whether the historical rainfall is within the rainfall threshold range; if yes, mark the rainfall state as a non-extreme rainfall state; if no, mark the rainfall state as an extreme rainfall state; The temperature extreme state, wind speed extreme state, light extreme state and rainfall extreme state are marked as extreme states; the temperature state, wind speed state, light state and rainfall state are combined to obtain the weather state; the extreme states appearing in the weather state are analyzed to obtain the historical extreme weather.

3. The extreme weather-based new energy regional power prediction system according to claim 2 is characterized in that: The analysis of extreme conditions in weather conditions to obtain historical extreme weather includes: Extract extreme weather conditions and extract extreme weather comparison table from the database; Match the extreme conditions with the extreme weather comparison table to obtain the historical extreme weather corresponding to the historical weather data.

4. The extreme weather-based new energy regional power prediction system according to claim 1, characterized in that: The power prediction model is constructed based on historical extreme weather, historical weather data and corresponding historical regional power, including: Extract historical extreme weather, historical weather data and corresponding historical regional power; Historical extreme weather, historical weather data and the corresponding historical regional power are used as training data and test data. The training data is used to train the neural network model, and the test data is used to test the trained neural network model. According to the test results, the parameters of the neural network model are adjusted to obtain a power prediction model whose input data is extreme weather and weather data, and whose output data is the corresponding regional power.

5. The extreme weather-based new energy regional power prediction system according to claim 1, characterized in that: The non-clean energy usage is predicted based on the predicted total power, historical regional power, historical power generation data, historical weather data and predicted weather data, including: Extract forecast total power, historical regional power, historical power generation data, historical weather data, and forecast weather data; Match the historical regional power and historical power generation data corresponding to historical extreme weather; Identify the predicted weather state of the predicted weather data, and match the predicted weather state with the extreme weather comparison table to obtain the predicted extreme weather; Determine whether the predicted extreme weather is the same as the historical extreme weather; if yes, mark the corresponding historical power generation data as matching power generation means; if no, mark the corresponding historical power generation data as not matching power generation means; The matching power is obtained according to the matching power generation means; the non-clean energy power is obtained by subtracting the matching power from the corresponding predicted total power; and the non-clean energy consumption is obtained according to the non-clean energy power.

6. The extreme weather-based new energy regional power prediction system according to claim 5, characterized in that: The obtaining of matching power according to matching power generation means comprises: Extracting matching power generation means; the matching power generation means include solar power generation, hydropower generation, wind power generation and corresponding power generation under extreme weather conditions; The average value of solar power generation is calculated to obtain solar power, the average value of hydroelectric power generation is calculated to obtain hydroelectric power, and the average value of wind power generation is calculated to obtain wind power; Combine solar power, hydro power and wind power to get matching power.

Images